Johannes
commited on
Commit
·
0e2e0a2
1
Parent(s):
d86b9d7
small change
Browse files
app.py
CHANGED
|
@@ -54,7 +54,8 @@ Demo by <a href='https://huggingface.co/johko' target='_blank'>Johannes (johko)
|
|
| 54 |
|
| 55 |
|
| 56 |
description = """<p style="text-align: center;">This is an interactive demo for the <a href="https://scikit-learn.org/stable/auto_examples/cluster/plot_segmentation_toy.html#sphx-glr-auto-examples-cluster-plot-segmentation-toy-py">Spectral clustering for image segmentation tutorial</a> from scikit-learn.
|
| 57 |
-
</br></br>
|
|
|
|
| 58 |
</br>The circles should ideally be close together(connected), to let the algorithm work correctly.
|
| 59 |
</br>As the demo uses k-means to determine the centroids of the circles exactly, you also need to specify the number of circles you want to get.
|
| 60 |
</br></br><b>What is Spectral Image clustering?</b> From the tutorial:
|
|
|
|
| 54 |
|
| 55 |
|
| 56 |
description = """<p style="text-align: center;">This is an interactive demo for the <a href="https://scikit-learn.org/stable/auto_examples/cluster/plot_segmentation_toy.html#sphx-glr-auto-examples-cluster-plot-segmentation-toy-py">Spectral clustering for image segmentation tutorial</a> from scikit-learn.
|
| 57 |
+
</br></br><b>How To Use</b>
|
| 58 |
+
</br>The demo lets you mark places in the input where the centers of circles should be. The circles should then be segmented from one another using Spectral Image Clustering.
|
| 59 |
</br>The circles should ideally be close together(connected), to let the algorithm work correctly.
|
| 60 |
</br>As the demo uses k-means to determine the centroids of the circles exactly, you also need to specify the number of circles you want to get.
|
| 61 |
</br></br><b>What is Spectral Image clustering?</b> From the tutorial:
|